I thought you get less power in clouds but ok

Derek Sivers has a very simple and direct implementation for static comments.

It’s 12, looks good to me.

I was today old when I learned that the software’s called btop++, not just btop :)

hunter2

it doesn’t look like *s to me

asd

No, I meant the “Anna’s archive” bit, and “seed for 2.1+ ratio” and turn it off and on again - what’s that about?

(sorry for ressurecting the thread, not used to checking notifications here)

You ever got anything so good you could publish?

Well, the API angle is similar to Space Traders

Sounds like there’s a story behind this, where could I read more?

Yes but if they do find a poor shmuck that wants the job, they can hope he’ll undervalue himself and ask for even less.

left-pad as a service.

It’s probably AI-supported slop.

(Not to be confused with our premium product, ParticleServices, which just shoot neutrinos around one by one.)

No, it’s just that it doesn’t know if it’s right or wrong.

How “AI” learns is they go through a text - say blog post - and turn it all into numbers. E.g. word “blog” is 5383825526283. Word “post” is 5611004646463. Over huge amount of texts, a pattern is emerging that the second number is almost always following the first number. Basically statistics. And it does that for all the words and word combinations it found - immense amount of text are needed to find all those patterns. (Fun fact: That’s why companies like e.g. OpenAI, which makes ChatGPT need hundreds of millions of dollars to “train the model” - they need enough computer power, storage, memory to read the whole damn internet.)

So now how do the LLMs “understand”? They don’t, it’s just a bunch of numbers and statistics of which word (turned into that number, or “token” to be more precise) follows which other word.

So now. Why do they hallucinate?

How they get your question, how they work, is they turn over all your words in the prompt to numbers again. And then go find in their huge databases, which words are likely to follow your words.

They add in a tiny bit of randomness, they sometimes replace a “closer” match with a synonym or a less likely match, so they even seen real.

They add “weights” so that they would rather pick one phrase over another, or e.g. give some topics very very small likelihoods - think pornography or something. “Tweaking the model”.

But there’s no knowledge as such, mostly it is statistics and dice rolling.

So the hallucination is not “wrong”, it’s just statisticaly likely that the words would follow based on your words.

Did that help?

You never review code when you have no time to do an actual review? Looks good to me :)

Gangaacrupt?

Is that pronounced as gokoze?

shaking my (trademark) head?

So, send’em a dicpic and you’re in :)